Paper Info
Title
LANMC - LSTM-Assisted Non-Rigid Motion Correction on FPGA for Calcium Image Stabilization.
Abstract
Calcium imaging is an emerging technique for visualizing and recording neural population activity at large scale in vivo. Non-rigid motion correction is a critical step in the calcium image analysis pipeline due to non-uniform deformations of the brain tissue during the data collection. However, existing non-rigid motion correction algorithms are costly in computation time and energy, and it is hard to implement such algorithm in real time on an embedded device. In this paper, we propose LANMC, an LSTM-assisted non-rigid motion correction method for real-time calcium image stabilization. This method reduces the computational cost by using the LSTM inference to predict the non-rigid motion. Based on this method, we demonstrate a non-rigid motion correction implementation for real-time calcium image stabilization on FPGA. Experimental results show that the non-rigid motion correction can be accomplished within 80 µs on the Ultra96 under 300 MHz frequency, and the latency outperforms that on a 12-thread CPU by 82x.
Year
DOI
Venue
2019
10.1145/3289602.3293919
FPGA
Keywords
Field
DocType
Calcium image, long short-term memory (LSTM), motion correction
Population,Computer vision,Calcium,Latency (engineering),Computer science,Image stabilization,Field-programmable gate array,Real-time computing,Calcium imaging,Artificial intelligence,Motion correction,Computation
Conference
ISBN
Citations 
PageRank 
978-1-4503-6137-8
2
0.44
References 
Authors
8
3
Name
Order
Citations
PageRank
Zhe Chen121.12
Hugh T. Blair2226.43
Jason Cong37069515.06